© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2275
    Prev
    Next
    INDEX
    Explanations

    references to economic crises and their impacts on communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.30
    1.2%
    604
    +0.12
    0.5%
    1445
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    617
    +0.30
    0.07
    764
    +0.12
    0.03
    509
    +0.10
    0.08
    Negative Logits
    <bos>
    -2.91
     intersper
    -1.29
     encomp
    -1.12
     indestru
    -1.07
     unve
    -1.03
     suscep
    -1.02
     disreg
    -0.99
     reconno
    -0.97
     reluct
    -0.96
     shenan
    -0.95
    POSITIVE LOGITS
     Bekasi
    0.81
     padang
    0.64
    pylab
    0.62
     Tangerang
    0.61
     taha
    0.59
     problems
    0.59
    iomanip
    0.57
    stdarg
    0.57
     soulign
    0.56
     Palembang
    0.55
    Activations Density 1.584%

    No Known Activations